{"id":"https://openalex.org/W3021620182","doi":"https://doi.org/10.1109/icbslp47725.2019.202055","title":"A Bangla Text-to-Speech System using Deep Neural Networks","display_name":"A Bangla Text-to-Speech System using Deep Neural Networks","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W3021620182","doi":"https://doi.org/10.1109/icbslp47725.2019.202055","mag":"3021620182"},"language":"en","primary_location":{"id":"doi:10.1109/icbslp47725.2019.202055","doi":"https://doi.org/10.1109/icbslp47725.2019.202055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbslp47725.2019.202055","pdf_url":null,"source":{"id":"https://openalex.org/S7407106936","display_name":"International Conference on Bangla Speech and Language Processing (ICBSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Bangla Speech and Language Processing (ICBSLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070386193","display_name":"Rajan Saha Raju","orcid":"https://orcid.org/0009-0003-8382-7758","observed_orcids":["https://orcid.org/0009-0003-8382-7758"]},"institutions":[{"id":"https://openalex.org/I133190216","display_name":"Shahjalal University of Science and Technology","ror":"https://ror.org/05hm0vv72","country_code":"BD","type":"education","lineage":["https://openalex.org/I133190216"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Rajan Saha Raju","raw_affiliation_strings":["Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","institution_ids":["https://openalex.org/I133190216"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh","institution_ids":["https://openalex.org/I133190216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002304137","display_name":"Prithwiraj Bhattacharjee","orcid":"https://orcid.org/0000-0001-9300-9351","observed_orcids":["https://orcid.org/0000-0001-9300-9351"]},"institutions":[{"id":"https://openalex.org/I133190216","display_name":"Shahjalal University of Science and Technology","ror":"https://ror.org/05hm0vv72","country_code":"BD","type":"education","lineage":["https://openalex.org/I133190216"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Prithwiraj Bhattacharjee","raw_affiliation_strings":["Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","institution_ids":["https://openalex.org/I133190216"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh","institution_ids":["https://openalex.org/I133190216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027209017","display_name":"Arif Ahmad","orcid":"https://orcid.org/0000-0002-2649-8981","observed_orcids":["https://orcid.org/0000-0002-2649-8981"]},"institutions":[{"id":"https://openalex.org/I133190216","display_name":"Shahjalal University of Science and Technology","ror":"https://ror.org/05hm0vv72","country_code":"BD","type":"education","lineage":["https://openalex.org/I133190216"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Arif Ahmad","raw_affiliation_strings":["Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","institution_ids":["https://openalex.org/I133190216"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh","institution_ids":["https://openalex.org/I133190216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103824075","display_name":"Mohammad Shahidur Rahman","orcid":"https://orcid.org/0009-0002-1862-2978","observed_orcids":["https://orcid.org/0009-0002-1862-2978"]},"institutions":[{"id":"https://openalex.org/I133190216","display_name":"Shahjalal University of Science and Technology","ror":"https://ror.org/05hm0vv72","country_code":"BD","type":"education","lineage":["https://openalex.org/I133190216"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mohammad Shahidur Rahman","raw_affiliation_strings":["Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shahjalal University of Science and Technology,Department of Computer Science and Engineering,Sylhet,Bangladesh","institution_ids":["https://openalex.org/I133190216"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh","institution_ids":["https://openalex.org/I133190216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133190216"],"apc_list":null,"apc_paid":null,"fwci":0.4065,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.62621626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bengali-language","display_name":"Bengali language","score":0.699999988079071},{"id":"https://openalex.org/keywords/statistical-parametric-speech-synthesis","display_name":"statistical parametric speech synthesis","score":0.875},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.921999990940094},{"id":"https://openalex.org/keywords/speech-dataset","display_name":"speech dataset","score":0.49399998784065247},{"id":"https://openalex.org/keywords/pronunciation-dictionary","display_name":"pronunciation dictionary","score":0.7649999856948853},{"id":"https://openalex.org/keywords/linguistic-feature-extraction","display_name":"linguistic feature extraction","score":0.6399999856948853},{"id":"https://openalex.org/keywords/synthetic-speech","display_name":"synthetic speech","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9614173769950867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038582801818848},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6706202626228333},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6681739687919617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6342329382896423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302123069763184},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6216216683387756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5934910178184509},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5806678533554077},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5798289179801941},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43570196628570557},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4107154309749603},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11638933420181274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icbslp47725.2019.202055","doi":"https://doi.org/10.1109/icbslp47725.2019.202055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbslp47725.2019.202055","pdf_url":null,"source":{"id":"https://openalex.org/S7407106936","display_name":"International Conference on Bangla Speech and Language Processing (ICBSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Bangla Speech and Language Processing (ICBSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1552314771","https://openalex.org/W1600722501","https://openalex.org/W1604626467","https://openalex.org/W1995100505","https://openalex.org/W2043003570","https://openalex.org/W2100167690","https://openalex.org/W2102003408","https://openalex.org/W2134973740","https://openalex.org/W2150658333","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2294797155","https://openalex.org/W2398366824","https://openalex.org/W2400063444","https://openalex.org/W2402539796","https://openalex.org/W2413439388","https://openalex.org/W2471520273","https://openalex.org/W2508996402","https://openalex.org/W2519091744","https://openalex.org/W2544446511","https://openalex.org/W2591927543","https://openalex.org/W2598638573","https://openalex.org/W2603532017","https://openalex.org/W2619368999","https://openalex.org/W2765486990","https://openalex.org/W2766812927","https://openalex.org/W2901997113","https://openalex.org/W2902181397","https://openalex.org/W2946200149","https://openalex.org/W2951815364","https://openalex.org/W2955448105","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W6712610176","https://openalex.org/W6749489859","https://openalex.org/W6756197946","https://openalex.org/W6765987481","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W3192805203","https://openalex.org/W4413700826","https://openalex.org/W2891336433","https://openalex.org/W7117463111","https://openalex.org/W3209763111","https://openalex.org/W3208642953","https://openalex.org/W3167116800","https://openalex.org/W2548152648","https://openalex.org/W2346107407","https://openalex.org/W7119480141"],"abstract_inverted_index":{"We":[0,52,73,119],"present":[1],"a":[2,24,54,76],"Deep":[3],"Neural":[4],"Network":[5],"(DNN)":[6],"based":[7],"statistical":[8],"parametric":[9],"Text-to-Speech":[10],"(TTS)":[11],"system":[12,27,98,143],"for":[13,37,49,83,95,111],"Bangla":[14,38,150,161],"(also":[15],"known":[16],"as":[17],"Bengali).":[18],"A":[19],"first":[20],"step":[21],"in":[22],"building":[23],"DNN-based":[25],"TTS":[26,39,122,151,162],"is":[28,40,91,154],"having":[29],"large":[30],"speech":[31,35,58],"data.":[32],"Since":[33],"good":[34],"dataset":[36,48,126],"not":[41],"available":[42,159],"publicly,":[43],"we":[44],"created":[45],"our":[46,50,89,125,142],"own":[47],"system.":[51,163],"prepared":[53,75],"phonetically":[55],"rich":[56],"studio-quality":[57],"database":[59,68],"containing":[60],"more":[61],"than":[62,147],"40":[63],"hours":[64],"of":[65,70,80],"speech.":[66],"The":[67],"consists":[69],"12,500":[71],"utterances.":[72],"also":[74],"pronunciation":[77],"dictionary":[78],"(lexicon)":[79],"1,35,000":[81],"words":[82],"front-end":[84],"text":[85],"processing,":[86],"which,":[87],"to":[88,116,156],"knowledge,":[90],"the":[92,148,157],"largest":[93],"lexicon":[94],"Bangla.":[96],"Our":[97],"extracts":[99],"linguistic":[100,114],"features":[101,115],"from":[102],"input":[103],"text.":[104],"Then":[105],"it":[106],"uses":[107],"deep":[108],"neural":[109],"networks":[110],"mapping":[112],"these":[113],"acoustic":[117],"features.":[118],"developed":[120],"two":[121],"voices":[123],"using":[124],"-":[127],"one":[128,131],"male":[129],"and":[130,136,153],"female":[132],"voice.":[133],"Both":[134],"objective":[135],"subjective":[137],"evaluation":[138],"tests":[139],"show":[140],"that":[141],"performs":[144],"significantly":[145],"better":[146],"traditional":[149],"systems":[152],"comparable":[155],"commercially":[158],"best":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-05-13T00:00:00"}